CN109870461B - Electronic components quality detection system - Google Patents
Electronic components quality detection system Download PDFInfo
- Publication number
- CN109870461B CN109870461B CN201910247051.7A CN201910247051A CN109870461B CN 109870461 B CN109870461 B CN 109870461B CN 201910247051 A CN201910247051 A CN 201910247051A CN 109870461 B CN109870461 B CN 109870461B
- Authority
- CN
- China
- Prior art keywords
- image
- electronic component
- detected
- module
- gray
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a quality detection system for electronic components, which comprises: the device comprises an image acquisition module, an image screening module, an electronic component classification module, an image processing module and a defect detection module. The system is more convenient and faster, the extracted characteristic data of the electronic component to be detected does not need to be compared with the prestored defect data of each type of electronic component, the defect detection time is greatly shortened, the quality detection efficiency is improved, and the errors of manual identification are also reduced.
Description
Technical Field
The invention relates to the technical field of quality detection, in particular to a quality detection system for electronic components.
Background
With the development of modern science and technology, more and more fields become more intelligent, and various novel electronic devices emerge endlessly, so the demand for electronic components is continuously rising, and the detection task of manufacturers on the product quality is also becoming harder. In the process of producing electronic components such as chips, batteries, circuit boards and the like, the defects such as collision, scratch, dirt and the like can be generated, the defects often do not show abnormality in performance test, but in the actual use process, the electronic components often face high-load work or a worse working environment, and the defects are very likely to influence the performance of the components and even generate potential safety hazards. In the past decades, the industrial production process has been greatly improved, but the defect detection of the product appearance is still mainly performed in a manual detection mode, which not only causes the inconsistency of the detection standard due to personal subjective factors, but also causes visual fatigue due to long-time detection, generates erroneous judgment or missing judgment, and the manual detection also consumes a lot of time, wastes a lot of manpower, and has low detection efficiency.
Disclosure of Invention
In order to solve the problems, the invention provides a quality detection system for an electronic component.
The purpose of the invention is realized by adopting the following technical scheme:
an electronic component quality inspection system, the system comprising: the device comprises an image acquisition module, an image screening module, an electronic component classification module, an image processing module and a defect detection module;
the image acquisition module configured to: acquiring a plurality of original images of an electronic component to be detected, and transmitting the original images to the image screening module;
the image screening module configured to: performing quality evaluation on the received multiple original images, and selecting the original image with the best image quality to respectively send to the electronic component classification module and the image processing module;
the electronic component sorting module is configured to: extracting the contour information of the electronic component to be detected from the received original image, comparing the contour information with the pre-stored standard contour information of each type of electronic component, and determining the type of the electronic component to be detected;
the image processing module configured to: carrying out noise reduction processing on the received original image, and extracting characteristic data describing the electronic component to be detected from the noise-reduced original image;
the defect detection module configured to: and calling pre-stored defect data corresponding to the type of the electronic component to be detected, identifying the extracted characteristic data of the electronic component to be detected according to the called defect data, and judging whether the electronic component to be detected has a defect and a corresponding defect type if the electronic component to be detected has the defect.
Preferably, the system further comprises: the cloud server is in communication connection with the electronic component classification module and the defect detection module, and standard outline information of various types of electronic components and various corresponding defect data are prestored in the cloud server;
the cloud server is further used for storing the classification result of the electronic component classification module.
Preferably, the system further comprises a terminal device communicatively connected to the defect detection module, the terminal device being configured to: the defect detection module is used for receiving the detection result of the defect detection module so that quality inspection personnel can know whether the electronic component to be detected has defects or not in time and the corresponding defect type if the electronic component to be detected has the defects.
Preferably, the extracting the profile information of the electronic component to be detected from the received original image, and comparing the profile information with the pre-stored standard profile information of each type of electronic component to determine the type of the electronic component to be detected includes:
(1) carrying out image segmentation on the received original image, and removing a background image to obtain a target image only containing the electronic component to be detected;
(2) normalizing the obtained target image to adjust the target image to a preset standard size, and extracting profile information of the electronic component to be detected from the target image, wherein the profile information comprises: curvature values of edge points of the electronic element to be detected;
(3) and comparing the extracted outline information of the electronic component to be detected with the pre-stored standard outline information of each type of electronic component to determine the type of the electronic component to be detected.
Preferably, the image segmentation is performed on the received original image, specifically:
(1) carrying out graying processing on a received original image, and dividing the original image into a plurality of image blocks with the size of S multiplied by T;
(2) performing threshold segmentation on each image block, wherein the threshold calculation formula of the image block is as follows:
when in use
The pixel point is the pixel point of the target image, otherwise, the pixel point is the pixel point of the background image;
in the formula (I), the compound is shown in the specification,
is the r1Line r2Optimal threshold, Th, of image blocks of a column0Is a preset global segmentation threshold value and is a global segmentation threshold value,
is the r1Line r2The gray value of the pixel point at the t-th column of the s-th row in the image block of the column,
is the r1Line r2The average gray value of the image blocks of a column,
is the r1Line r2Variance, σ, of the gray values of the image blocks of the columns0Is the variance of the gray values of the grayed original image,
is the r1Line r2Mean of the grey values of the image blocks of the columns, u0α and β are weight factors which are larger than zero and satisfy that α + β is 1;
(3) and acquiring pixel points of all target images, wherein a set formed by the pixel points of the target images is the target image.
Preferably, the image acquisition module is an image sensor and/or a CCD camera.
The invention has the beneficial effects that: the system is more convenient and faster, the extracted characteristic data of the electronic component to be detected does not need to be compared with the prestored defect data of each type of electronic component, the defect detection time is greatly shortened, the quality detection efficiency is improved, and the errors of manual identification are also reduced.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
Fig. 1 is a frame structure diagram of an electronic component quality inspection system according to an embodiment of the present invention;
fig. 2 is a frame structure diagram of the image processing module 4 according to the embodiment of the present invention.
Reference numerals: the system comprises an image acquisition module 1, an image screening module 2, an electronic component classification module 3, an image processing module 4, a defect detection module 5, a cloud server 6, a terminal device 7, a denoising unit 41 and a feature extraction unit 42.
Detailed Description
The invention is further described with reference to the following examples.
Fig. 1 shows an electronic component quality inspection system, which includes: the system comprises an image acquisition module 1, an image screening module 2, an electronic component classification module 3, an image processing module 4 and a defect detection module 5;
the image acquisition module 1 is configured to: acquiring a plurality of original images of the electronic component to be detected, and transmitting the original images to the image screening module 2;
the image screening module 2 is configured to: performing quality evaluation on the received multiple original images, and selecting the original image with the best image quality to respectively send to the electronic component classification module 3 and the image processing module 4;
the electronic component sorting module 3 is configured to: extracting the contour information of the electronic component to be detected from the received original image, comparing the contour information with the pre-stored standard contour information of each type of electronic component, and determining the type of the electronic component to be detected;
the image processing module 4 is configured to: carrying out noise reduction processing on the received original image, and extracting characteristic data describing the electronic component to be detected from the noise-reduced original image;
the defect detection module 5 is configured to: and according to the classification result of the electronic component classification module 3, pre-stored defect data of the electronic component to be detected is retrieved, the extracted feature data of the electronic component to be detected is identified according to the retrieved defect data, and whether the electronic component to be detected has a defect or not and a corresponding defect type if the electronic component to be detected has the defect are judged. Specifically, the defect detection module 5 retrieves all possible defect data corresponding to the type from the cloud server 6 according to the type of the electronic component to be detected determined by the electronic component classification module 3, compares the retrieved defect data with the feature data of the electronic component to be detected extracted by the image processing module 4 one by one, and further determines whether the electronic component to be detected has a defect and the corresponding defect type if the electronic component to be detected has the defect. If it is
The electronic component to be tested has defects and belongs to the u-th class of defects, wherein,
is the characteristic vector of the d-type defect data of the w-type electronic component,
and lambda is a preset similarity factor which is a characteristic vector of characteristic data of the electronic component to be detected.
Preferably, the system further comprises: the cloud server 6 is in communication connection with the electronic component classification module 3 and the defect detection module 5, and standard outline information of various types of electronic components and various types of corresponding defect data are prestored in the cloud server 6;
the cloud server 6 is further used for storing the classification result of the electronic component classification module.
Preferably, the system further comprises a terminal device 7 communicatively connected to said defect detection module 5, said terminal device 7 being configured to: and the defect detection module is used for receiving the detection result of the defect detection module 5 so that quality inspection personnel can know whether the electronic component to be detected has defects and the corresponding defect type if the electronic component to be detected has defects in time.
Preferably, the extracting the profile information of the electronic component to be detected from the received original image, and comparing the profile information with the pre-stored standard profile information of each type of electronic component to determine the type of the electronic component to be detected includes:
(1) carrying out image segmentation on the received original image, and removing a background image to obtain a target image only containing the electronic component to be detected;
(2) normalizing the obtained target image to adjust the target image to a preset standard size, and extracting profile information of the electronic component to be detected from the target image, wherein the profile information comprises: curvature values of edge points of the electronic element to be detected;
(3) and comparing the extracted outline information of the electronic component to be detected with the pre-stored standard outline information of each type of electronic component to determine the type of the electronic component to be detected.
Preferably, the image segmentation is performed on the received original image, specifically:
(1) carrying out graying processing on a received original image, and dividing the original image into a plurality of image blocks with the size of S multiplied by T;
(2) performing threshold segmentation on each image block, wherein the threshold calculation formula of the image block is as follows:
when in use
The pixel point is the pixel point of the target image, otherwise, the pixel point is the pixel point of the background image;
in the formula (I), the compound is shown in the specification,
is the r1Line r2Optimal threshold, Th, of image blocks of a column0Is a preset global segmentation threshold value and is a global segmentation threshold value,
is the r1Line r2The gray value of the pixel point at the t-th column of the s-th row in the image block of the column,
is the r1Line r2The average gray value of the image blocks of a column,
is the r1Line r2Variance, σ, of the gray values of the image blocks of the columns0Is the variance of the gray values of the grayed original image,
is the r1Line r2Mean of the grey values of the image blocks of the columns, u0α and β are weight factors which are larger than zero and satisfy that α + β is 1;
(3) and acquiring pixel points of all target images, wherein a set formed by the pixel points of the target images is the target image.
Has the advantages that: the method has the advantages that the original image obtained through screening is divided into the image blocks, different thresholds are selected to carry out segmentation processing on the image blocks, the algorithm is more flexible, the self-adaption is strong, the thresholds are jointly determined by the gray values of the image blocks, the gray values of the grayed original image and the preset global segmentation threshold, the method can be free from the interference of the external environment, such as the interference of illumination, shielding, image dirt and the like, the method is favorable for obtaining the image area related to the electronic component, further favorable for obtaining the edge of the complete electronic component to be detected, and convenient for accurately identifying the type of the electronic component to be detected subsequently.
Preferably, the image acquisition module is an image sensor and/or a CCD camera.
In an optional embodiment, the quality evaluation of the received multiple original images specifically includes:
and respectively evaluating the quality of each original image to obtain the image quality score value of each original image, wherein the higher the image quality score value is, the better the quality of the original image is represented.
Taking the original image X as an example, the quality evaluation includes:
(1) converting an original image X into a gray image X ', filtering the gray image X' by adopting a low-pass filter of a Gaussian model to obtain a filtered image, and taking the filtered image as a reference image Y;
(2) dividing the grayscale image X 'and the reference image Y into image blocks of A × B size, and recording the image blocks of the grayscale image X' as: x is the number ofk(K ═ 1, 2.. times, K), denote image blocks of the reference image Y as: y isk(K ═ 1,2,. and K), where K is the number of image blocks; image block xkThe calculation formula of the mean value and the standard deviation of the gray value is as follows:
in the formula，
For image block xkThe mean value of the gray values is,
for image block xkThe middle coordinate is the gray value of the pixel point at (a, b),
for image block xkThe standard deviation of (a); calculating the mean value and standard deviation of the gray values of all image blocks in the gray image X' and the reference image Y in the same way;
(3) calculating the image quality score value of the gray image X 'by using the following formula according to the obtained gray value mean value and standard deviation of all image blocks in the gray image X' and the reference image Y:
in the formula, ρX'Is the image quality score value of the grayscale image X', which can be used to characterize the image quality score value of the original image X.
Has the advantages that: the preferred embodiment calculates the image quality score value of the original image X by using the method, and further evaluates the image quality of the original image X by introducing the mean value and the standard deviation of each image block of the grayscale image X' and the reference image Y.
In an alternative embodiment, the image processing module 4 includes a denoising unit 41 and a feature extraction unit 42;
a denoising unit 41 configured to: carrying out noise reduction processing on the received original image;
a feature extraction unit 42 configured to: and extracting characteristic data describing the electronic component to be detected from the denoised original image.
In an optional embodiment, the denoising processing on the received original image includes:
(1) carrying out graying processing on the received original image to obtain a corresponding grayed image;
(2) selecting a sliding window omega with the size of MxM, calculating a denoising estimation value of a central pixel point p (M, n) of the sliding window omega by using a denoising function, and replacing the calculated denoising estimation value with a gray value of a corresponding pixel point in the grayed image to obtain the gray value of the denoised pixel point p (M, n), wherein the denoising function is as follows:
in the formula, Gp' (m, n) is a denoised estimated value of the center pixel point p (m, n), Gp(m, n) is the gray value of the central pixel point p (m, n) in the grayed image, ωq(i, j) is the weighting coefficient of the pixel point q (i, j), and the pixel point q (i, j) refers to: within the sliding window Ω, the remaining pixels, G, excluding the center pixel p (m, n)q(i, j) is the gray value of pixel point q (i, j) | | · luminance2The square of the norm is represented as,
is the gray scale gradient value of the pixel point q (i, j) in the horizontal direction,
the gray scale gradient value of the pixel point q (i, j) in the vertical direction, ξ, delta are set fixed parameters, gamma1、γ2Is a weight factor which satisfies γ1+γ2＝1。
(3) And traversing all pixel points of the gray image, wherein a set formed by denoising estimated values of all the pixel points is the denoised original image.
Has the advantages that: when denoising is carried out on the screened original image, the denoising gray value of the central pixel point in the sliding window omega is solved through the step (2), the algorithm not only considers the gray value at the position of the central pixel point, but also considers the influence of other pixel points in the sliding window omega on the denoising gray value of the central pixel point, the random noise of the central pixel point can be filtered in a self-adaptive mode in the process, the denoising estimation value of the corresponding pixel point is estimated to serve as the denoising gray value of the pixel point, in addition, the denoising process can effectively remove the random noise in the image while image detail information is kept, the denoising original image with high definition is obtained, the follow-up characteristic parameters of the electronic component to be detected can be conveniently and accurately extracted, and further, the defect of the electronic component to be detected is accurately identified.
The invention has the beneficial effects that: the system is more convenient and faster, the extracted characteristic data of the electronic component to be detected does not need to be compared with the prestored defect data of each type of electronic component, the defect detection time is greatly shortened, the quality detection efficiency is improved, and the errors of manual identification are also reduced.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (4)
1. An electronic component quality detection system, comprising: the device comprises an image acquisition module, an image screening module, an electronic component classification module, an image processing module and a defect detection module;
the image acquisition module configured to: acquiring a plurality of original images of an electronic component to be detected, and transmitting the original images to the image screening module;
the image screening module configured to: the quality evaluation is carried out on the received multiple original images, the original image with the best image quality is selected and is respectively sent to the electronic component classification module and the image processing module;
the electronic component sorting module is configured to: extracting the contour information of the electronic component to be detected from the received original image, comparing the contour information with the pre-stored standard contour information of each type of electronic component, and determining the type of the electronic component to be detected;
the image processing module configured to: carrying out noise reduction processing on the received original image, and extracting characteristic data describing the electronic component to be detected from the noise-reduced original image;
the defect detection module configured to: calling pre-stored defect data corresponding to the type of the electronic component to be detected, identifying the extracted characteristic data of the electronic component to be detected according to the called defect data, and judging whether the electronic component to be detected has a defect and a corresponding defect type if the electronic component to be detected has the defect;
the quality evaluation of the original image is specifically as follows:
(1) converting an original image X into a gray image X ', filtering the gray image X' by adopting a low-pass filter of a Gaussian model to obtain a filtered image, and taking the filtered image as a reference image Y;
(2) dividing the grayscale image X' and the reference image Y into A × B sizesAnd image blocks of the grayscale image X' are recorded as: x is the number ofk(K ═ 1, 2.. times, K), denote image blocks of the reference image Y as: y isk(K ═ 1,2,. and K), where K is the number of image blocks; image block xkThe calculation formula of the mean value and the standard deviation of the gray value is as follows:
in the formula (I), the compound is shown in the specification,
for image block xkThe mean value of the gray values is,
for image block xkThe middle coordinate is the gray value of the pixel point at (a, b),
for image block xkThe standard deviation of (a); calculating the mean value and standard deviation of the gray values of all image blocks in the gray image X' and the reference image Y in the same way;
(3) calculating the image quality score value of the gray image X 'by using the following formula according to the obtained gray value mean value and standard deviation of all image blocks in the gray image X' and the reference image Y:
in the formula, ρX'Is the image quality score value of the grayscale image X', which can be used to characterize the image quality score value of the original image X;
the method for determining the type of the electronic component to be detected comprises the following steps of extracting the contour information of the electronic component to be detected from a received original image, comparing the contour information with pre-stored standard contour information of various types of electronic components, and determining the type of the electronic component to be detected, wherein the method comprises the following steps:
(1) carrying out image segmentation on the received original image, and removing a background image to obtain a target image only containing the electronic component to be detected;
(2) normalizing the obtained target image to adjust the target image to a preset standard size, and extracting profile information of the electronic component to be detected from the target image, wherein the profile information comprises: curvature values of edge points of the electronic element to be detected;
(3) comparing the extracted outline information of the electronic component to be detected with pre-stored standard outline information of various types of electronic components to determine the type of the electronic component to be detected;
the image segmentation is performed on the received original image, specifically:
(1) carrying out graying processing on a received original image, and dividing the original image into a plurality of image blocks with the size of S multiplied by T;
(2) performing threshold segmentation on each image block, wherein the threshold calculation formula of the image block is as follows:
when in use
The pixel point is the pixel point of the target image, otherwise, the pixel point is the pixel point of the background image;
in the formula (I), the compound is shown in the specification,
is the r1Line r2Optimal threshold, Th, of image blocks of a column0Is a preset global segmentation threshold value and is a global segmentation threshold value,
is the r1Line r2The gray value of the pixel point at the t-th column of the s-th row in the image block of the column,
is the r1Line r2The average gray value of the image blocks of a column,
is the r1Line r2Variance, σ, of the gray values of the image blocks of the columns0Is the variance of the gray values of the grayed original image,
is the r1Line r2Mean of the grey values of the image blocks of the columns, u0α and β are weight factors which are larger than zero and satisfy that α + β is 1;
(3) and acquiring pixel points of all target images, wherein a set formed by the pixel points of the target images is the target image.
2. The system for inspecting quality of electronic components of claim 1, further comprising: the cloud server is in communication connection with the electronic component classification module and the defect detection module, and standard outline information of various types of electronic components and various corresponding defect data are prestored in the cloud server;
the cloud server is further used for storing the classification result of the electronic component classification module.
3. The system for inspecting quality of electronic components as claimed in claim 1, further comprising a terminal device communicatively connected to the defect detection module, the terminal device configured to: the defect detection module is used for receiving the detection result of the defect detection module so that quality inspection personnel can know whether the electronic component to be detected has defects or not in time and the corresponding defect type if the electronic component to be detected has the defects.
4. The system for detecting the quality of the electronic component as claimed in claim 1, wherein the image acquisition module is an image sensor and/or a CCD camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910247051.7A CN109870461B (en) | 2019-03-29 | 2019-03-29 | Electronic components quality detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910247051.7A CN109870461B (en) | 2019-03-29 | 2019-03-29 | Electronic components quality detection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109870461A CN109870461A (en) | 2019-06-11 |
| CN109870461B true CN109870461B (en) | 2020-04-24 |
Family
ID=66921592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910247051.7A Expired - Fee Related CN109870461B (en) | 2019-03-29 | 2019-03-29 | Electronic components quality detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109870461B (en) |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570445B (en) * | 2019-09-09 | 2022-03-25 | 上海联影医疗科技股份有限公司 | Image segmentation method, device, terminal and readable medium |
| CN111243041A (en) * | 2020-02-29 | 2020-06-05 | 山峰 | Conveyor belt timing driving system based on big data |
| CN111412949B (en) * | 2020-04-13 | 2022-04-01 | 杭州思元智能科技有限公司 | Electronic component detection method and detection device |
| CN111855668A (en) * | 2020-07-17 | 2020-10-30 | 上海洪朴信息科技有限公司 | Product defect detecting system |
| CN111999308A (en) * | 2020-08-27 | 2020-11-27 | 银河水滴科技（北京）有限公司 | Defect detection control method, control device and control system |
| CN113052819A (en) * | 2021-03-25 | 2021-06-29 | 贵州电网有限责任公司 | Circuit defect picture acquisition and analysis system and acquisition and analysis method |
| CN113378478B (en) * | 2021-06-30 | 2022-11-22 | 安庆机床有限公司 | Automatic control system of ball making machine |
| CN113850285A (en) * | 2021-07-30 | 2021-12-28 | 安徽继远软件有限公司 | Power transmission line defect identification method and system based on edge calculation |
| CN113808116A (en) * | 2021-09-24 | 2021-12-17 | 无锡精质视觉科技有限公司 | Intelligent detection method and system based on image recognition and product detection system |
| CN114137345B (en) * | 2021-11-25 | 2024-05-31 | 深圳市三田技术科技有限公司 | FPC stress screening and detecting system |
| CN114943739B (en) * | 2022-07-26 | 2022-10-21 | 山东三微新材料有限公司 | Aluminum pipe quality detection method |
| CN115239692B (en) * | 2022-08-12 | 2023-06-27 | 广东科学技术职业学院 | Electronic component detection method and system based on image recognition technology |
| CN115100203B (en) * | 2022-08-25 | 2022-11-18 | 山东振鹏建筑钢品科技有限公司 | Method for detecting quality of steel bar polishing and rust removal |
| CN115294314B (en) * | 2022-09-26 | 2022-12-30 | 南通蘅田电子科技有限公司 | Electronic component surface defect identification method |
| CN116012380B (en) * | 2023-03-27 | 2023-06-16 | 中江立江电子有限公司 | Insulator defect detection method, device, equipment and medium |
| CN117457520B (en) * | 2023-10-25 | 2024-05-31 | 武汉昕微电子科技有限公司 | Defect detection method and system for semiconductor component |
| CN117151551B (en) * | 2023-10-31 | 2024-02-06 | 江苏富松模具科技有限公司 | Stamping quality management method and system for stator and rotor silicon steel sheets |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103413150A (en) * | 2013-06-28 | 2013-11-27 | 广东电网公司电力科学研究院 | Power line defect diagnosis method based on visible light image |
| CN106940904A (en) * | 2017-03-14 | 2017-07-11 | 深圳汇通智能化科技有限公司 | Attendance checking system based on recognition of face and speech recognition |
| CN107389701A (en) * | 2017-08-22 | 2017-11-24 | 西北工业大学 | A kind of PCB visual defects automatic checkout system and method based on image |
| CN107607540A (en) * | 2017-07-26 | 2018-01-19 | 广东工业大学 | A kind of T-shirt on-line checking and method for separating based on machine vision |
| CN108171900A (en) * | 2017-12-29 | 2018-06-15 | 潘永森 | A kind of ATM cash withdrawal system |
| CN108205663A (en) * | 2017-12-29 | 2018-06-26 | 李文清 | A kind of vehicle startup system based on fingerprint recognition |
| CN109507192A (en) * | 2018-11-02 | 2019-03-22 | 江苏理工学院 | A kind of magnetic core detection method of surface flaw based on machine vision |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101478697A (en) * | 2009-01-20 | 2009-07-08 | 中国测绘科学研究院 | Quality evaluation method for video lossy compression |
| CN103870832B (en) * | 2014-03-21 | 2017-11-03 | 浙江宇视科技有限公司 | Vehicle global feature extracting method and vehicle model recognition methods |
| CN107481374B (en) * | 2017-08-18 | 2020-08-14 | 浙江浦江梅花锁业集团有限公司 | Intelligent terminal fingerprint unblock door opener |
-
2019
- 2019-03-29 CN CN201910247051.7A patent/CN109870461B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103413150A (en) * | 2013-06-28 | 2013-11-27 | 广东电网公司电力科学研究院 | Power line defect diagnosis method based on visible light image |
| CN106940904A (en) * | 2017-03-14 | 2017-07-11 | 深圳汇通智能化科技有限公司 | Attendance checking system based on recognition of face and speech recognition |
| CN107607540A (en) * | 2017-07-26 | 2018-01-19 | 广东工业大学 | A kind of T-shirt on-line checking and method for separating based on machine vision |
| CN107389701A (en) * | 2017-08-22 | 2017-11-24 | 西北工业大学 | A kind of PCB visual defects automatic checkout system and method based on image |
| CN108171900A (en) * | 2017-12-29 | 2018-06-15 | 潘永森 | A kind of ATM cash withdrawal system |
| CN108205663A (en) * | 2017-12-29 | 2018-06-26 | 李文清 | A kind of vehicle startup system based on fingerprint recognition |
| CN109507192A (en) * | 2018-11-02 | 2019-03-22 | 江苏理工学院 | A kind of magnetic core detection method of surface flaw based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109870461A (en) | 2019-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109870461B (en) | Electronic components quality detection system | |
| CN114937055B (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| CN110163853B (en) | Edge defect detection method | |
| CN107543828B (en) | Workpiece surface defect detection method and system | |
| CN107507173B (en) | No-reference definition evaluation method and system for full-slice image | |
| CN111383209A (en) | Unsupervised flaw detection method based on full convolution self-encoder network | |
| CN107490582B (en) | Assembly line workpiece detection system | |
| CN114998314B (en) | PCB defect detection method based on computer vision | |
| CN109060842B (en) | Citrus surface defect detection method based on surface fitting correction | |
| CN115100206B (en) | Printing defect identification method for textile with periodic pattern | |
| CN111415339B (en) | Image defect detection method for complex texture industrial product | |
| CN111539927B (en) | Detection method of automobile plastic assembly fastening buckle missing detection device | |
| CN115797473B (en) | Concrete forming evaluation method for civil engineering | |
| CN113155839A (en) | Steel plate outer surface defect online detection method based on machine vision | |
| CN111563896A (en) | Image processing method for catenary anomaly detection | |
| CN110807763A (en) | Method and system for detecting ceramic tile surface bulge | |
| CN112561875A (en) | Photovoltaic cell panel coarse grid detection method based on artificial intelligence | |
| CN114332081B (en) | Textile surface abnormity determination method based on image processing | |
| Yeh et al. | A wavelet-based approach in detecting visual defects on semiconductor wafer dies | |
| CN102118547A (en) | Image weighted filtering method | |
| CN112017109A (en) | Online ferrographic video image bubble elimination method | |
| CN115018785A (en) | Hoisting steel wire rope tension detection method based on visual vibration frequency identification | |
| CN114820626A (en) | Intelligent detection method for automobile front part configuration | |
| Lin et al. | A new prediction method for edge detection based on human visual feature | |
| CN116934746B (en) | Scratch defect detection method, system, equipment and medium thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200327 Address after: No.2 standard workshop, Siyang Economic Development Zone (east area), Suqian City, Jiangsu Province Applicant after: Siyang Hengrun Electronics Co.,Ltd. Address before: 518000 B710-1, 7th Floor, Silver Star Science and Technology Building, 1301 Guanlan Street Sightseeing Road, Longhua District, Shenzhen City, Guangdong Province Applicant before: SHENZHEN ASIM ELECTRONIC Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200424 |